© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128702
    Prev
    Next
    INDEX
    Explanations

    legal followed by consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     olmak
    0.45
     generation
    0.43
     scissor
    0.41
     træ
    0.40
     writer
    0.40
    衔
    0.39
    0.39
     disconnected
    0.38
     methane
    0.37
     powert
    0.37
    POSITIVE LOGITS
    岦
    0.65
    resposta
    0.52
    ᆹ
    0.52
     ಆದರೆ
    0.51
     بعد
    0.51
    ទៀ
    0.51
    ۔
    0.51
     Políticas
    0.50
    yyum
    0.49
     Фурга
    0.49
    Activations Density 0.004%

    No Known Activations